Evolving Insect Locomotion using Non-uniform Cellular Automata

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
4 Author(s)

This article presents a model for the evolution of locomotion behavior in a simulated insect. In our model, locomotion is defined over a discrete state space using non-uniform cellular automata. The architecture of the model is inspired from the distributed model for leg coordination proposed by Cruse. We apply a genetic algorithm to a population of non-uniform cellular automata to evolve locomotion behaviors. We demostrate that this model can be used to evolve several commonly observed gaits of insects. Additionally, we show that the evolutionary process yielded periodic attractors which are invariant from the initial conditions